Messages in this thread | | | Date | Mon, 29 Mar 2010 15:20:57 +0100 | Subject | Re: [RFC,PATCH 2/2] perf, x86: Utilize the LBRs for machine/oops debugging | From | Stephane Eranian <> |
| |
On Mon, Mar 29, 2010 at 3:13 PM, Peter Zijlstra <peterz@infradead.org> wrote: > On Mon, 2010-03-29 at 13:47 +0100, Stephane Eranian wrote: >> On Mon, Mar 29, 2010 at 1:20 PM, Peter Zijlstra <a.p.zijlstra@chello.nl> wrote: >> > The LBRs are relatively cheap to keep enabled and provide some history >> > to OOPSen, also some CPUs are reported to keep them over soft-reset, >> > which allows us to use them to debug things like tripple faults. >> > >> > Therefore introduce a boot option: lbr_debug=on, which always enable >> > the LBRs and will print the LBRs on CPU init and die(). >> > >> >> When this is enabled, it will prevent changing the LBR configuration to >> record only selected branches. Unless you are willing to accept filtered >> content in the kernel dump. > > Sure, but since we don't support that silly config reg anyway that's > pretty much not an issue ;-) > I will provide a patch to make it available. This is needed for certain measurements.
| |